Author name cluster

Hao Ma

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

18 papers

2 author rows

EAAI Journal 2026 Journal Article

Advanced fetal cerebellar vermis segmentation and gestational age prediction in ultrasound imaging for prenatal neural development assessment

Qifeng Wang
Dan Zhao
Hao Ma
Bin Liu

In prenatal diagnostics, accurate segmentation of the Cerebellar Vermis (CV) in fetal brain ultrasound images is essential for assessing fetal neural development. Traditional manual segmentation methods are prone to omissions and misdiagnoses, and even minor measurement errors can significantly affect fetal health and diagnostic accuracy. To address these challenges, we propose the Fetal Brain Feature Enhanced UNet (FB-FEUNet), an advanced segmentation network enhancing CV segmentation precision through specialized modules: the Week Embedding Module (WEM) for incorporating gestational timing, the Fusion Feature Attention Module (FFAM) for multisource feature integration, the Week Conditional Attention Module (WCAM) for gestational age-aware adjustments, and the Fusion Constraint Module (FCM) to enhance segmentation accuracy. The model was trained on the Fetal Brain Cerebellar Vermis Dataset (FB-CV), a curated collection of fetal brain ultrasound images designed to support robust evaluation. Experimental results demonstrate that FB-FEUNet achieves a Dice Coefficient of 0. 8670 and an Intersection over Union of 0. 7686, outperforming state-of-the-art methods in both accuracy and stability, while also providing faster inference times. These findings confirm the effectiveness of FB-FEUNet in addressing segmentation challenges and highlight its clinical potential to improve diagnostic accuracy, reduce manual errors, and improve fetal neural development assessments.

Details DOI

EWRL Workshop 2025 Workshop Paper

Constraint-Aware Diffusion Guidance for Imitation Learning

Hao Ma
Sabrina Bodmer
Andrea Carron
Melanie Zeilinger
Michael Muehlebach

We propose Constraint-Aware Diffusion Guidance (CoDiG), a constraint-aware imitation learning framework based on conditional diffusion models. Unlike conventional imitation learning methods, which often fail to generalize to unseen or constrained environments, CoDiG enforces safety and physical feasibility during inference via barrier function guidance. Our method learns from a limited number of expert demonstrations without reward supervision or environment interaction, and is capable of generating safe and feasible trajectories in real time. A warm-start strategy further accelerates sampling by reusing previous outputs. We evaluate CoDiG on a miniature autonomous racing platform in a challenging obstacle avoidance task, demonstrating robust generalization, near time-optimal performance, and 100% success rate in dynamic scenarios. Our results highlight the potential of constraint-aware diffusion models as a data-efficient and deployable solution for safe imitation learning in robotics.

PDF

EAAI Journal 2025 Journal Article

Low-light image enhancement using dual cross attention

Yudi Ruan
Hao Ma
Di Ma
Weikai Li
Xiao Wang

Low-light image enhancement (LLIE) aims to improve the perceptibility and interpretability of images captured in poorly illuminated environments. Existing LLIE methods often fail to capture the local self-similarity and long-range dependencies at the same time, causing the loss of complementary information between multiple modules or network layers, ultimately resulting in the loss of image details. To alleviate this issue, we design a hierarchical mutual Enhancement via a dual cross-attention transformer (ECAFormer), which introduces an architecture that enables concurrent propagation and interaction of multiple disentangling features. To capture the local self-similarity, we design a Dual Multi-head Self-Attention (DMSA), which leverages the disentangled visual and semantic features across different scales, allowing them to guide and complement each other. Further, a cross-scale DMSA block is incorporated to capture residual connections, thereby integrating cross-layer information and capturing the long-range dependencies. Experimental results show that the ECAFormer reaches competitive performance across multiple benchmarks, yielding nearly a 3. 7% improvement in Peak Signal-to-Noise Ratio (PSNR) over the suboptimal method, demonstrating the effectiveness of information interaction in LLIE. For facilitating the efforts to replicate our results, our implementation is available on GitHub 1 1 https: //github. com/ruanyudi/ECAFormer.

Details DOI

EWRL Workshop 2025 Workshop Paper

Online Optimization of Closed-Loop Control Systems

Hao Ma
Melanie Zeilinger
Michael Muehlebach

We propose a novel gradient-based online optimization framework for solving stochastic programming problems that frequently arise in the context of cyber-physical and robotic systems. We establish the connection between our algorithms and the cyber-physical systems through the classic two-degree-of-freedom control loop. We also incorporate an approximate model of the dynamics as prior knowledge into the learning process, and characterize the impact of modeling errors in the system dynamics on the convergence rate of the algorithms. We show that even rough estimates of the dynamics can significantly improve the convergence of our algorithms. Finally, we evaluate our algorithms in simulations of a flexible beam and a four-legged walking robot.

PDF

ICRA Conference 2025 Conference Paper

Stochastic Trajectory Prediction Under Unstructured Constraints

Hao Ma
Zhiqiang Pu
Shijie Wang 0006
Boyin Liu
Huimu Wang
Yanyan Liang 0001
Jianqiang Yi

Trajectory prediction facilitates effective planning and decision-making, while constrained trajectory prediction integrates regulation into prediction. Recent advances in constrained trajectory prediction focus on structured constraints by constructing optimization objectives. However, handling unstructured constraints is challenging due to the lack of differentiable formal definitions. To address this, we propose a novel method for constrained trajectory prediction using a conditional generative paradigm, named Controllable Trajectory Diffusion (CTD). The key idea is that any trajectory corresponds to a degree of conformity to a constraint. By quantifying this degree and treating it as a condition, a model can implicitly learn to predict trajectories under unstructured constraints. CTD employs a pre-trained scoring model to predict the degree of conformity (i. e. , a score), and uses this score as a condition for a conditional diffusion model to generate trajectories. Experimental results demonstrate that CTD achieves high accuracy on the ETH/UCY and SDD benchmarks. Qualitative analysis confirms that CTD ensures adherence to unstructured constraints and can predict trajectories that satisfy combinatorial constraints.

Details

JBHI Journal 2025 Journal Article

Transformer 3: A Pure Transformer Framework for fMRI-Based Representations of Human Brain Function

Xiaoxi Tian
Hao Ma
Yun Guan
Le Xu
Jiangcong Liu
Lixia Tian

Effective representation learning is essential for neuroimage-based individualized predictions. Numerous studies have been performed on fMRI-based individualized predictions, leveraging sample-wise, spatial, and temporal interdependencies hidden in fMRI data. However, these studies failed to fully utilize the effective information hidden in fMRI data, as only one or two types of the interdependencies were analyzed. To effectively extract representations of human brain function through fully leveraging the three types of the interdependencies, we establish a pure transformer-based framework, Transformer 3, leveraging transformer's strong ability to capture interdependencies within the input data. Transformer 3 consists mainly of three transformer modules, with the Batch Transformer module used for addressing sample-wise similarities and differences, the Region Transformer module used for handling complex spatial interdependencies among brain regions, and the Time Transformer module used for capturing temporal interdependencies across time points. Experiments on age, IQ, and sex predictions based on two public datasets demonstrate the effectiveness of the proposed Transformer 3. As the only hypothesis is that sample-wise, spatial, and temporal interdependencies extensively exist within the input data, the proposed Transformer 3 can be widely used for representation learning based on multivariate time-series. Furthermore, the pure transformer framework makes it quite convenient for understanding the driving factors underlying the predictive models based on Transformer 3.

Details DOI

AAAI Conference 2025 Conference Paper

Vision-Based Generic Potential Function for Policy Alignment in Multi-Agent Reinforcement Learning

Hao Ma
Shijie Wang
Zhiqiang Pu
Siyao Zhao
Xiaolin Ai

Guiding the policy of multi-agent reinforcement learning to align with human common sense is a difficult problem, largely due to the complexity of modeling common sense as a reward, especially in complex and long-horizon multi-agent tasks. Recent works have shown the effectiveness of reward shaping, such as potential-based rewards, to enhance policy alignment. The existing works, however, primarily rely on experts to design rule-based rewards, which are often labor-intensive and lack a high-level semantic understanding of common sense. To solve this problem, we propose a hierarchical vision-based reward shaping method. At the bottom layer, a visual-language model (VLM) serves as a generic potential function, guiding the policy to align with human common sense through its intrinsic semantic understanding. To help the policy adapts to uncertainty and changes in long-horizon tasks, the top layer features an adaptive skill selection module based on a visual large language model (vLLM). The module uses instructions, video replays, and training records to dynamically select suitable potential function from a pre-designed pool. Besides, our method is theoretically proven to preserve the optimal policy. Extensive experiments conducted in the Google Research Football environment demonstrate that our method not only achieves a higher win rate but also effectively aligns the policy with human common sense.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning

Hao Ma
Tianyi Hu
Zhiqiang Pu
Boyin Liu
Xiaolin Ai
Yanyan Liang
Min Chen

Reinforcement learning (RL) has emerged as a pivotal technique for fine-tuning large language models (LLMs) on specific tasks. However, prevailing RL fine-tuning methods predominantly rely on PPO and its variants. Though these algorithms are effective in general RL settings, they often exhibit suboptimal performance and vulnerability to distribution collapse when applied to the fine-tuning of LLMs. In this paper, we propose CORY, extending the RL fine-tuning of LLMs to a sequential cooperative multi-agent reinforcement learning framework, to leverage the inherent coevolution and emergent capabilities of multi-agent systems. In CORY, the LLM to be fine-tuned is initially duplicated into two autonomous agents: a pioneer and an observer. The pioneer generates responses based on queries, while the observer generates responses using both the queries and the pioneer’s responses. The two agents are trained together. During training, the agents exchange roles periodically, fostering cooperation and coevolution between them. Experiments evaluate CORY's performance by fine-tuning GPT-2 and Llama-2 under subjective and objective reward functions on the IMDB Review and GSM8K datasets, respectively. Results show that CORY outperforms PPO in terms of policy optimality, resistance to distribution collapse, and training robustness, thereby underscoring its potential as a superior methodology for refining LLMs in real-world applications.

PDF Details DOI

JBHI Journal 2023 Journal Article

A Siamese Network With Node Convolution for Individualized Predictions Based on Connectivity Maps Extracted From Resting-State fMRI Data

Le Xu
Hao Ma
Yun Guan
Jiangcong Liu
Huifang Huang
Yang Zhang
Lixia Tian

Deep learning has demonstrated great potential for objective diagnosis of neuropsychiatric disorders based on neuroimaging data, which includes the promising resting-state functional magnetic resonance imaging (RS-fMRI). However, the insufficient sample size has long been a bottleneck for deep model training for the purpose. In this study, we proposed a Siamese network with node convolution (SNNC) for individualized predictions based on RS-fMRI data. With the involvement of Siamese network, which uses sample pair (rather than a single sample) as input, the problem of insufficient sample size can largely be alleviated. To adapt to connectivity maps extracted from RS-fMRI data, we applied node convolution to each of the two branches of the Siamese network. For regression purposes, we replaced the contrastive loss in classic Siamese network with the mean square error loss and thus enabled Siamese network to quantitatively predict label differences. The label of a test sample can be predicted based on any of the training samples, by adding the label of the training sample to the predicted label difference between them. The final prediction for a test sample in this study was made by averaging the predictions based on each of the training samples. The performance of the proposed SNNC was evaluated with age and IQ predictions based on a public dataset (Cam-CAN). The results indicated that SNNC can make effective predictions even with a sample size of as small as 40, and SNNC achieved state-of-the-art accuracy among a variety of deep models and standard machine learning approaches.

Details DOI

IROS Conference 2023 Conference Paper

Adversarial Driving Behavior Generation Incorporating Human Risk Cognition for Autonomous Vehicle Evaluation

Zhen Liu 0054
Hang Gao
Hao Ma
Shuo Cai
Yunfeng Hu 0003
Ting Qu 0001
Hong Chen 0003
Xun Gong 0007

Autonomous vehicle (AV) evaluation has been the subject of increased interest in recent years both in industry and in academia. This paper focuses on the development of a novel framework for generating adversarial driving behavior of background vehicle interfering against the AV to expose effective and rational risky events. Specifically, the adversarial behavior is learned by a reinforcement learning (RL) approach incorporated with the cumulative prospect theory (CPT) which allows representation of human risk cognition. Then, the extended version of deep deterministic policy gradient (DDPG) technique is proposed for training the adversarial policy while ensuring training stability as the CPT action-value function is leveraged. A comparative case study regarding the cut-in scenario is conducted on a high fidelity Hardware-in-the-Loop (HiL) platform and the results demonstrate the adversarial effectiveness to infer the weakness of the tested AV.

Details

IROS Conference 2023 Conference Paper

Data-Efficient Online Learning of Ball Placement in Robot Table Tennis

Philip Tobuschat
Hao Ma
Dieter Büchler
Bernhard Schölkopf
Michael Muehlebach

We present an implementation of an online op-timization algorithm for hitting a predefined target when returning ping-pong balls with a table tennis robot. The online algorithm optimizes over so-called interception policies, which define the manner in which the robot arm intercepts the ball. In our case, these are composed of the state of the robot arm (position and velocity) at interception time. Gradient information is provided to the optimization algorithm via the mapping from the interception policy to the landing point of the ball on the table, which is approximated with a black-box and a grey-box approach. Our algorithm is applied to a robotic arm with four degrees of freedom that is driven by pneumatic artificial muscles. As a result, the robot arm is able to return the ball onto any predefined target on the table after about 2–5 iterations. We highlight the robustness of our approach by showing rapid convergence with both the black-box and the grey-box gradients. In addition, the small number of iterations required to reach close proximity to the target also underlines the sample efficiency. A demonstration video can be found here: https://youtu.be/VC3KJoCss0k.

Details

AAAI Conference 2022 Conference Paper

RID-Noise: Towards Robust Inverse Design under Noisy Environments

Jia-Qi Yang
Ke-Bin Fan
Hao Ma
De-Chuan Zhan

From an engineering perspective, a design should not only perform well in an ideal condition, but should also resist noises. Such a design methodology, namely robust design, has been widely implemented in the industry for product quality control. However, classic robust design requires a lot of evaluations for a single design target, while the results of these evaluations could not be reused for a new target. To achieve a data-efficient robust design, we propose Robust Inverse Design under Noise (RID-Noise), which can utilize existing noisy data to train a conditional invertible neural network (cINN). Specifically, we estimate the robustness of a design parameter by its predictability, measured by the prediction error of a forward neural network. We also define a sample-wise weight, which can be used in the maximum weighted likelihood estimation of an inverse model based on a cINN. With the visual results from experiments, we clearly justify how RID-Noise works by learning the distribution and robustness from data. Further experiments on several real-world benchmark tasks with noises confirm that our method is more effective than other state-of-the-art inverse design methods. Code and supplementary is publicly available at https: //github. com/ThyrixYang/rid-noise-aaai22

PDF Details

NeurIPS Conference 2021 Conference Paper

Luna: Linear Unified Nested Attention

Xuezhe Ma
Xiang Kong
Sinong Wang
Chunting Zhou
Jonathan May
Hao Ma
Luke Zettlemoyer

The quadratic computational and memory complexities of the Transformer's attention mechanism have limited its scalability for modeling long sequences. In this paper, we propose Luna, a linear unified nested attention mechanism that approximates softmax attention with two nested linear attention functions, yielding only linear (as opposed to quadratic) time and space complexity. Specifically, with the first attention function, Luna packs the input sequence into a sequence of fixed length. Then, the packed sequence is unpacked using the second attention function. As compared to a more traditional attention mechanism, Luna introduces an additional sequence with a fixed length as input and an additional corresponding output, which allows Luna to perform attention operation linearly, while also storing adequate contextual information. We perform extensive evaluations on three benchmarks of sequence modeling tasks: long-context sequence modelling, neural machine translation and masked language modeling for large-scale pretraining. Competitive or even better experimental results demonstrate both the effectiveness and efficiency of Luna compared to a variety of strong baseline methods including the full-rank attention and other efficient sparse and dense attention methods.

PDF Details

ICRA Conference 2014 Conference Paper

Human level walking gait modeling and analysis based on semi-Markov process

Hao Ma
Wei-Hsin Liao

Evaluation of individual gait pattern is important for both abnormal gait diagnosis and gait rehabilitation in mobility impaired people. In this paper, semi-Markov process (SMP) is applied to model and analyze human gait in level walking. Gait states are detected from ground reaction forces (GRFs), and gait cycles are described as state transitions in a gait Markov chain (GMC) with sojourn times. Several gait features are defined and online estimated based on the SMP model. With this model, abnormal gait patterns are further analyzed and indexes for gait abnormality assessment are proposed. Experiments of gait analyses with proposed method are conducted on subjects with different health conditions. Results show that individual gait pattern can be successfully obtained and evaluated. Potential applications in gait diagnosis and powered lower limb orthosis (PLLO) control for gait assistance are also discussed.

Details

TIST Journal 2011 Journal Article

Learning to recommend with explicit and implicit social relations

Hao Ma
Irwin King
Michael R. Lyu

Recommender systems have been well studied and developed, both in academia and in industry recently. However, traditional recommender systems assume that all the users are independent and identically distributed; this assumption ignores the connections among users, which is not consistent with the real-world observations where we always turn to our trusted friends for recommendations. Aiming at modeling recommender systems more accurately and realistically, we propose a novel probabilistic factor analysis framework which naturally fuses the users' tastes and their trusted friends' favors together. The proposed framework is quite general, and it can also be applied to pure user-item rating matrix even if we do not have explicit social trust information among users. In this framework, we coin the term social trust ensemble to represent the formulation of the social trust restrictions on the recommender systems. The complexity analysis indicates that our approach can be applied to very large datasets since it scales linearly with the number of observations, while the experimental results show that our method outperforms state-of-the-art approaches.

Details DOI

AAAI Conference 2011 Conference Paper

Social Recommendation Using Low-Rank Semidefinite Program

Jianke Zhu
Hao Ma
Chun Chen
Jiajun Bu

The most critical challenge for the recommendation system is to achieve the high prediction quality on the large scale sparse data contributed by the users. In this paper, we present a novel approach to the social recommendation problem, which takes the advantage of the graph Laplacian regularization to capture the underlying social relationship among the users. Differently from the previous approaches, that are based on the conventional gradient descent optimization, we formulate the presented graph Laplacian regularized social recommendation problem into a low-rank semideﬁnite program, which is able to be efﬁciently solved by the quasi-Newton algorithm. We have conducted the empirical evaluation on a large scale dataset of high sparsity, the promising experimental results show that our method is very effective and efﬁcient for the social recommendation task.

PDF Details

AAAI Conference 2010 Conference Paper

Diversifying Query Suggestion Results

Hao Ma
Michael Lyu
Irwin King

In order to improve the user search experience, Query Suggestion, a technique for generating alternative queries to Web users, has become an indispensable feature for commercial search engines. However, previous work mainly focuses on suggesting relevant queries to the original query while ignoring the diversity in the suggestions, which will potentially dissatisfy Web users’ information needs. In this paper, we present a novel unified method to suggest both semantically relevant and diverse queries to Web users. The proposed approach is based on Markov random walk and hitting time analysis on the query-URL bipartite graph. It can effectively prevent semantically redundant queries from receiving a high rank, hence encouraging diversities in the results. We evaluate our method on a large commercial clickthrough dataset in terms of relevance measurement and diversity measurement. The experimental results show that our method is very effective in generating both relevant and diverse query suggestions.

PDF Details

AAAI Conference 2010 Conference Paper

UserRec: A User Recommendation Framework in Social Tagging Systems

Tom Zhou
Hao Ma
Michael Lyu
Irwin King

Social tagging systems have emerged as an effective way for users to annotate and share objects on the Web. However, with the growth of social tagging systems, users are easily overwhelmed by the large amount of data and it is very difficult for users to dig out information that he/she is interested in. Though the tagging system has provided interestbased social network features to enable the user to keep track of other users’ tagging activities, there is still no automatic and effective way for the user to discover other users with common interests. In this paper, we propose a User Recommendation (UserRec) framework for user interest modeling and interest-based user recommendation, aiming to boost information sharing among users with similar interests. Our work brings three major contributions to the research community: (1) we propose a tag-graph based community detection method to model the users’ personal interests, which are further represented by discrete topic distributions; (2) the similarity values between users’ topic distributions are measured by Kullback-Leibler divergence (KL-divergence), and the similarity values are further used to perform interestbased user recommendation; and (3) by analyzing users’ roles in a tagging system, we find users’ roles in a tagging system are similar to Web pages in the Internet. Experiments on tagging dataset of Web pages (Yahoo! Delicious) show that UserRec outperforms other state-of-the-art recommender system approaches.

PDF Details